I aim at building multimodal interactive AI systems that can not only ground and reason over the external world signals, to understand human language, but also assist humans in decision-making and efficiently solving social concerns, e.g., robot.
As steps towards this goal, my research interests include but are not limited to Multimodal Large Language Models, Video Generation and Multimodal Agents.
[2024/03] I will be joining ByteDance AML, Seattle, USA, as a research intern this summer.
[2024/01] 1 paper is accepted by ICLR 2024.
[2023/11]π₯π₯π₯ We release a GitHub repository to promote medical Large Language Models research with the vision of applying LLM to real-life medical scenarios: A Practical Guide for Medical Large Language Models.
[2023/11]π₯π₯π₯ How could LMMs contribute to social good? We are excited to release a new preliminary explorations of GPT-4V(ison) for social multimedia: GPT-4V(ision) as A Social Media Analysis Engine.
[2023/09]Join the VIStA Lab as a Ph.D. student working on vision and language.
[2023/07]1 paper is accepted by ACMMM 2023.
[2023/05]I was awarded the 2023 Peking University Excellent Graduation Thesis.
[2023/04]1 paper is accepted by TIP 2023.
[2023/04]1 paper is accepted by IJCAI 2023.
[2023/02]1 paper (Top 10% Highlight) is accepted by CVPR 2023.
[2022/09]1 paper is accepted by ICRA 2023.
[2022/09]1 paper (Spotlight) is accepted by NeurIPS 2022.
Education
University of Rochester (UR), USA
PH.D. Student in Computer Science • Sep. 2023 - Present
Advisor: Prof. Jiebo Luo
Peking University (PKU), China
Master Degree in Computer Science • Sep. 2020 - Jun. 2023
Advisors: Prof. Li Yuan and Prof. Jie Chen
University of Electronic Science and Technology of China (UESTC), China
Bachelor Degree in Software Engineering • Sep. 2016 - Jun. 2020
Existing text-to-video models have not adequately encoded physical knowledge of the real world, thus generated videos tend to have limited motion and poor variations.
In this paper, we propose MagicTime, a metamorphic time-lapse video generation model, which learns real-world physics knowledge from time-lapse videos and implements metamorphic video generation.
Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach Shaofeng Zhang,
Jinfa Huang,
Qiang Zhou,
Zhibin Wang,
Fan Wang,
Jiebo Luo,
Junchi Yan Conference on International Conference on Learning Representations, ICLR 2024 (Review Rating: 866) [Paperlink], [Code] Area: Image Outpainting, Diffusion Model, GenAI
We have proposed PQDiff, which learns the positional relationships and pixel information at the
same time. Methodically, PQDiff can outpaint at any multiple in only one step, greatly increasing the
applicability of image outpainting.
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning Peng Jin,
Jinfa Huang,
Pengfei Xiong,
Shangxuan Tian,
Chang Liu,
Xiangyang Ji,
Li Yuan,
Jie Chen IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2023 (Highlight, Top 2.5%) [Paperlink], [Code] Area: Video-and-Language Representation, Machine Learning, Video-Text Retrieval, Video Captioning
To solve the problem of modality gap in video-text feature space, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations.
We use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases.
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations Peng Jin*,
Jinfa Huang*,
Fenglin Liu,
Xian Wu,
Shen Ge,
Guoli Song,
David A. Clifton,
Jie Chen Conference on Neural Information Processing Systems, NeurIPS 2022 (Spotlight Presentation, Top 5%) [Paperlink], [Code] Area: Video-and-Language Representation, Machine Learning, Video-Text Retrieval, Video Captioning
To solve the problem of the modality gap in video-text feature space, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. We use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases.
Selected Honors & Scholarships
Outstanding Graduate of University of Electronic Science and Technology of China (UESTC) , 2020
National Inspirational Scholarship, 2018
Selected entrant for Deepcamp 2020 (200 people worldwide), 2020
Outstanding Camper of Tencent Rhino Bird Elite Research Camp (24 people worldwide), 2020
Selected entrant for Google Machine Learning Winter Camp 2019 (100 people worldwide), 2019
China Collegiate Programming Contest (ACM-CCPC), JiLin, Bronze, 2018
Peking University Excellent Graduation Thesis (Top 10%), PKU 2023
Academic Service
PC Member: CVPR'23/24, NeurIPS'22/23, ICLR'23/24, ICCV'23, ACM MM'24, ECCV'24
Journal Reviewer: IEEE TCSVT, IEEE TPAMI
Personal Interests
Anime: As a pastime in my spare time, I watched a lot of Japanese anime about love, sports, and sci-fi.
Literature: My favorite writer is Xiaobo Wang, the wisdom of his life inspires me. My favorite philosopher is Friedrich Wilhelm Nietzsche, and I am grateful that his philosophy has accompanied me through many difficult times in my life.